One API for every AI model

Build with Claude, GPT, Gemini, Grok, Mistral or self-hosted Llama through a single OpenAI-compatible gateway. Pick the model, stream the tokens, ship faster.

Get your API key View the API

One API, every model

Claude, GPT, Gemini, Grok, Mistral and self-hosted Llama behind a single OpenAI-compatible endpoint. Swap models by changing one string.

Real-time streaming

Server-Sent Events stream tokens as they are generated — the same chat.completion.chunk frames your existing OpenAI client already understands.

Smart auto-routing

Pin a default model or let the Blue Model Router pick per request by cost, speed, quality or privacy — without touching your code.

Private by design

Route sensitive workloads to self-hosted models so data never leaves your environment. Rotate keys anytime from the console.

Model catalog

Choose the right model for the job

Every model is exposed through the same interface, priced and rated so you can trade off quality, speed and cost.

Quick start

Drop-in OpenAI-compatible

Already using the OpenAI SDK? Point the base URL at BB Developers, set your key, and you are done.

curl -N https://developers.bluebridge.es/api/ai/v1/chat \
  -H "Authorization: Bearer $BBC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "stream": true,
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Omit model to use your pinned default or auto-routing. Set "stream": false for a single JSON response.

Open the console